A gated 'skip the middle' Transformer fails to beat fewer-layer dense baselines on the cross-entropy/FLOPs trade-off at 12 layers and 10B tokens.
SwitchHead : Accelerating Transformers with Mixture-of-Experts Attention
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Learning to Skip the Middle Layers of Transformers
A gated 'skip the middle' Transformer fails to beat fewer-layer dense baselines on the cross-entropy/FLOPs trade-off at 12 layers and 10B tokens.